HPS-Det: Dynamic Sample Assignment with Hyper-Parameter Search for Object Detection
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ROAXKNDXrecord.jsonopen to challenge →
read the original abstract
Sample assignment plays a prominent part in modern object detection approaches. However, most existing methods rely on manual design to assign positive / negative samples, which do not explicitly establish the relationships between sample assignment and object detection performance. In this work, we propose a novel dynamic sample assignment scheme based on hyper-parameter search. We first define the number of positive samples assigned to each ground truth as the hyper-parameters and employ a surrogate optimization algorithm to derive the optimal choices. Then, we design a dynamic sample assignment procedure to dynamically select the optimal number of positives at each training iteration. Experiments demonstrate that the resulting HPS-Det brings improved performance over different object detection baselines. Moreover, We analyze the hyper-parameter reusability when transferring between different datasets and between different backbones for object detection, which exhibits the superiority and versatility of our method.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.